[BACKEND] Add bf16 & tf32 mma supports (on A100) (#426)

2022-01-12 02:20:31 +08:00
parent efdabe6073
commit 94a2e10fe5
17 changed files with 717 additions and 263 deletions
--- a/lib/codegen/pass.cc
+++ b/lib/codegen/pass.cc
@@ -85,7 +85,6 @@ std::unique_ptr<llvm::Module> add_passes_to_emit_bin(ir::module &ir, llvm::LLVMC
  allocation.run(ir);
  prefetch_s.run(ir);
  barriers.run(ir);
-  // ir.print(std::cout);
  isel.visit(ir, *llvm);
  shared_static = allocation.allocated_size();
  return llvm;